Exploring heuristics and assessing their impact in discrete choice experiments: a proof-of-principle

Area of Science:

• Health economics
• Behavioral economics
• Decision science

Background:

• Discrete Choice Experiments (DCEs) are widely used to model preferences in healthcare.
• DCEs traditionally assume rational decision-making based on Random Utility Theory (RUT).
• Real-world health choices can be complex, leading to heuristic-based decision-making that violates RUT.

Purpose of the Study:

• To demonstrate methods for identifying and assessing the impact of RUT-violating heuristics in DCE studies.
• To provide guidance on modeling heuristic-based behavior in health preference research.

Main Methods:

• Utilized three existing DCE studies to illustrate heuristic impact assessment.
• Developed a structured interview guide and rating instrument, informed by clinician and researcher input, to identify heuristics.
• Employed Latent-Class Models with restricted parameters to estimate heuristic effects alongside preference heterogeneity.

Main Results:

• Sensitivity analyses indicated that up to 22% of respondents may have used specific heuristics.
• Ignoring heuristics led to biased preference estimates; for instance, accounting for dominant decision-making increased willingness-to-pay for low-antibiotic-resistance treatments by €15.63.
• Heuristics significantly impacted marginal rates of substitution and predicted uptake.

Conclusions:

• Failure to account for RUT-violating heuristics in DCEs biases key preference measures and predictions.
• Researchers should incorporate heuristic assessment into sensitivity analyses for DCE studies.
• This approach enhances the robustness and accuracy of findings in health preference research.